Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3929 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.6226. Min Act: -0.1700
Data Index: 929182 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.6226. Min Act: -0.1700
Data Index: 6687894 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.6226. Min Act: -0.1700
Data Index: 759458 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5913. Min Act: -0.1700
Data Index: 4252589 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5913. Min Act: -0.1700
Data Index: 1180696 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5913. Min Act: -0.1700
Data Index: 4151121 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5913. Min Act: -0.1700
Data Index: 6792206 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 4240067 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 8089672 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 1552105 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 7879523 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 2597505 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 4212362 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 981522 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5600. Min Act: -0.1700
Data Index: 5140851 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 4268496 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 190843 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 3934339 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 7942514 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6226. Min Range: -3.6226
Max Act: 3.5443. Min Act: -0.1700
Data Index: 5725518 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19